From 6fca13f8d276673b3c47a9fb676783ba5b62a92e Mon Sep 17 00:00:00 2001 From: Jake Grigsby Date: Sun, 5 Nov 2023 01:28:22 -0500 Subject: [PATCH] update website paper link to be the latest version --- _site/feed.xml | 2 +- _site/index.html | 4 ++-- index.markdown | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/_site/feed.xml b/_site/feed.xml index 3a78fa5..db94b32 100644 --- a/_site/feed.xml +++ b/_site/feed.xml @@ -1 +1 @@ -Jekyll2023-11-05T00:59:27-05:00http://localhost:4000/feed.xmlAMAGOA simple and scalable agent for sequence-based RL \ No newline at end of file +Jekyll2023-11-05T01:27:22-05:00http://localhost:4000/feed.xmlAMAGOA simple and scalable agent for sequence-based RL \ No newline at end of file diff --git a/_site/index.html b/_site/index.html index ab7d2bd..a118f67 100644 --- a/_site/index.html +++ b/_site/index.html @@ -157,7 +157,7 @@

1The University of Texas at Austin    2NVIDIA Research   

-

Paper  |  Code

+

Paper  |  Code

@@ -276,7 +276,7 @@



-Finally, we evaluate AMAGO in the procedurally generated worlds of Crafter. Instructions are strings from a closed vocabulary of Crafter's achievement system, with added goals for navigation and block placement. Our agents need to generalize over thousands of unique goals in previously unseen environments, creating a highly general instruction-following agent. +Finally, we evaluate AMAGO in the procedurally generated worlds of Crafter. Instructions are strings from a closed vocabulary of Crafter's achievement system, with added goals for navigation and block placement.

diff --git a/index.markdown b/index.markdown index e7959b4..92ec2dc 100644 --- a/index.markdown +++ b/index.markdown @@ -168,7 +168,7 @@ highlight { 1The University of Texas at Austin    2NVIDIA Research    -

Paper  |  Code

+

Paper  |  Code

@@ -287,7 +287,7 @@ AMAGO handles meta-learning as a simple extension of zero-shot generalization, a

-Finally, we evaluate AMAGO in the procedurally generated worlds of Crafter. Instructions are strings from a closed vocabulary of Crafter's achievement system, with added goals for navigation and block placement. Our agents need to generalize over thousands of unique goals in previously unseen environments, creating a highly general instruction-following agent. +Finally, we evaluate AMAGO in the procedurally generated worlds of Crafter. Instructions are strings from a closed vocabulary of Crafter's achievement system, with added goals for navigation and block placement.